An internal pressure type anti-accumulation intelligent water purifier

Abstract

The present invention relates to the field of water purifiers, and particularly to an internal pressure type anti-accumulation intelligent water purifier, which includes a tap water inlet pipe, a plurality of water purifiers and an outlet pipe. The inlet pipes of the plurality of water purifiers are all conductively connected to the tap water inlet pipe, and the drain pipes of the plurality of water purifiers are all conductively connected to the outlet pipe. Electromagnetic valves are provided on the plurality of inlet pipes to control the conduction or closing of the inlet pipes. The internal pressure type anti-accumulation intelligent water purifier provided by the present invention can collect water purification data in real time, control the usage states of the plurality of water purifiers based on a trained machine learning model, realize the intelligent coordination of the working states of the plurality of water purifiers arranged in parallel, and achieve stable control of water quality and water volume.

Description

Technical Field

[0001] The invention relates to the field of water purifiers, and in particular to an internal pressure type anti-deposition intelligent water purifier. Background Art

[0002] As water pollution becomes more serious, the use of household water purifiers is gradually increasing. However, in some usage scenarios (such as commercial scenarios such as hotels and restaurants), a single household water purifier may not be able to meet large water demands or maintain stable operation for a long time. Therefore, the development of a parallel control system for multiple water purifiers has become the key to solving this problem.

[0003] The Chinese patent with publication number CN104418438A discloses a water purifier, wherein three or more filter elements are sequentially connected between the raw water inlet and the purified water outlet by a water pipe; among the above filter elements, at least two filter elements are connected in parallel, and the filter material filled in the parallel filter elements is activated carbon. In the water purifier of this scheme, two or more activated carbon filter elements are connected in parallel, which can reduce pressure loss and increase water flow rate. At the same time, the activated carbon preferably suitable for the water quality of Chinese tap water can effectively absorb organic matter in tap water, the water quality of the outlet is good, and the service life of the water purifier is long.

[0004] As in the above application, the traditional water purifier system sets up multiple filters in parallel, which can reduce pressure loss and increase water flow, but it cannot reasonably control the use status of each filter according to the actual filtering needs, that is, it is difficult to achieve flexible combination and intelligent regulation of the water purifier, which easily leads to uneven water quality or unstable flow. In order to improve the overall performance of the water purification system, an innovative control system is needed that can coordinate the working status of parallel water purifiers and achieve stable control of water quality and water quantity. Summary of the invention

[0005] In order to solve the above problems, the present invention provides an internal pressure anti-deposition intelligent water purifier.

[0006] The present invention adopts the following technical scheme: an internal pressure type anti-accumulation intelligent water purifier, comprising a tap water inlet pipe, a plurality of water purifiers and a water outlet pipe, the water inlet pipes of the plurality of water purifiers are interconnected with the tap water inlet pipe, the drainage pipes of the plurality of water purifiers are interconnected with the water outlet pipe, and the plurality of water inlet pipes are provided with solenoid valves for controlling the conduction or closing of the water inlet pipes, and further comprising:

[0007] The data collection module collects the historical water purification data of the water purifier and the corresponding number of water purifiers in use. The historical water purification data is collected when the water body meets the purification standards. The historical water purification data includes the flow data per unit time of the tap water inlet pipe, the water pressure data per unit time and the pollution coefficient;

[0008] The model training module trains and predicts a machine learning model for the number of water purifiers used based on historical water purification data, collects real-time water purification data, and predicts the number of water purifiers used based on the trained machine learning model.

[0009] The analysis and control module controls the solenoid valves installed on the corresponding number of inlet pipes to open based on the predicted number of water purifiers used.

[0010] As a further description of the above technical solution: The generation method of the pollution coefficient is as follows:

[0011]

[0012] In the formula, W x is the pollution coefficient, Z d is the turbidity of the water body in the tap water inlet pipe, PH is the acidity and alkalinity of the water body in the tap water inlet pipe, Ry is the dissolved oxygen content in the water body in the tap water inlet pipe, and are both weight coefficients, and are both greater than 0.

[0013] As a further description of the above technical solution: The training method of the machine learning model for predicting the number of water purifiers used includes:

[0014] Convert the collected historical water purification data of the water purifier and the number of water purifiers used into a corresponding set of feature vectors;

[0015] Use the collected historical water purification data of the water purifier as the input of the machine learning model. The machine learning model takes the number of water purifiers used corresponding to each set of historical water purification data as the output, takes the actual number of water purifiers used corresponding to each set of historical water purification data as the prediction target, and takes minimizing the loss function value of the machine learning model as the training target. Stop training when the loss function value of the machine learning model is less than or equal to the preset target loss value.

[0016] As a further description of the above technical solution: It also includes a backwashing component and a control unit;

[0017] The backwashing component includes:

[0018] A flushing water storage tank for storing filtered water for flushing the water purifier;

[0019] A flushing main pipe that is conductively connected to the flushing water storage tank;

[0020] A flushing branch pipe, one end of which is conductively connected to the flushing main pipe and the other end is conductively connected to the water purifier. A flushing volume control valve is provided on the flushing branch pipe.

[0021] As a further description of the above technical solution: The control unit includes:

[0022] A data recording module for recording the usage time information of several water purifiers within a unit cycle and the total water purification amount information of the water purifier within the unit cycle;

[0023] A data analysis module that generates a backwash coefficient based on the usage time information, total water purification amount information, unit cycle, and pollution coefficient, and determines and generates corresponding flushing water volume level information based on the backwash coefficient;

[0024] A control module that controls the opening time of the corresponding flushing volume control valve according to the flushing water volume level information.

[0025] As a further description of the above technical solution: The method for recording the usage time within a unit cycle and the total water purification amount information of the water purifier within the unit cycle for several water purifiers includes:

[0026] Mark several water purifiers arranged in parallel in sequence, and mark several water purifiers as J1, J2,..., J n ;

[0027] Obtain the usage time and total water purification amount of each water purifier within the unit cycle TZ;

[0028] Among them, the unit cycle TZ is the backwash cycle of several water purifiers. Preferably, it is one week (7 days).

[0029] As a further description of the above technical solution: The generation method of the backwash coefficient is as follows:

[0030]

[0031] Among them, FK n is the backwash coefficient of the nth water purifier, T n is the usage time of the nth water purifier within the unit cycle, SZ n is the total water purification amount of the nth water purifier within the unit cycle, TZ is the unit cycle data of the nth water purifier, and are both weight coefficients, and are both greater than 0.

[0032] As a further description of the above technical solution: The method for determining and generating corresponding flushing water volume level information based on the backwash coefficient includes:

[0033] Preset backwash coefficient thresholds F1 and F2, where F1 < F2;

[0034] When FK n≤F1, at this time, the data analysis module generates the first-level flushing water volume information;

[0035] When F1 < FK n <F2, at this time, the data analysis module generates the second-level flushing water volume information;

[0036] When FK n ≥F2, at this time, the data analysis module generates the third-level flushing water volume information;

[0037] Among them, the flushing water volumes corresponding to the first-level flushing water volume information, the second-level flushing water volume information, and the third-level flushing water volume information increase in sequence.

[0038] As a further description of the above technical solution: a sewage discharge pipe is conductively connected to the center of the bottom of the water purifier, which is used to discharge the sewage generated by backwashing, and a control valve is arranged on the sewage discharge pipe.

[0039] As a further description of the above technical solution: the water purifier is composed of a cylindrical outer casing and an internal pressure type filter element arranged inside the cylindrical outer casing.

[0040] Beneficial effects: An internal pressure type anti-accumulation intelligent water purifier provided by the present invention trains a machine learning model through the historical water body purification data of the water purifier and the number of water purifiers in use, predicts the usage status of several water purifiers per unit time based on the trained machine learning model, thereby collecting water body purification data in real time, and controlling the usage status of several water purifiers based on the trained machine learning model, realizing the intelligent coordinated operation status of several water purifiers arranged in parallel, and realizing the stable control of water quality and water volume;

[0041] Furthermore, through the setting of the backwashing assembly and the control unit, during use, the data recording module can obtain the usage time and net water volume of each water purifier, and then calculate the backwashing coefficient, thereby judging and generating corresponding flushing water volume level information according to the backwashing coefficient. Specifically, different flushing water volume level information of flushing water volumes is generated according to the usage time, net water volume of each water purifier, the time of the unit cycle, and the pollution coefficient of the water body, so as to realize targeted backwashing of each water purifier 2, ensure its flushing effect, and also save flushing water. Description of the Drawings

[0042] The following further explains the present invention in conjunction with the drawings and embodiments:

[0043] Figure 1 It is a schematic structural diagram of an internal pressure type anti-accumulation intelligent water purifier provided by an embodiment of the present invention;

[0044] Figure 2 It is a cross-sectional view of the water purifier provided by an embodiment of the present invention.

[0045] In the figure: 1, the tap water inlet pipe; 2, the water purifier; 201, the housing; 202, the filter element; 21, the inlet pipe; 211, the solenoid valve; 22, the drain pipe; 3, the outlet pipe; 4, the backwashing assembly; 41, the flushing water storage tank; 42, the main flushing pipe; 43, the branch flushing pipe; 44, the flushing volume control valve; 5, the sewage pipe; 51, the control valve. Detailed implementation mode

[0046] In order to make the technical means, creative features, achieved purposes and functions of the present invention easy to understand, the present invention will be further described below with reference to specific illustrations. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0047] Embodiment 1:

[0048] Please refer to Figure 1 - Figure 2 , an embodiment of the present invention provides a technical solution: an internal pressure type anti-accumulation intelligent water purifier, including a tap water inlet pipe 1, several water purifiers 2 and an outlet pipe 3. The inlet pipes 21 of several water purifiers 2 are all connected in a conducting manner with the tap water inlet pipe 1, and the drain pipes 22 of several water purifiers 2 are all connected in a conducting manner with the outlet pipe 3. Solenoid valves 211 are arranged on several inlet pipes 21 to control the conduction or closing of the inlet pipes 21. The water purifier 2 is composed of a cylindrical housing 201 and an internal pressure type filter element 202 arranged inside the cylindrical housing 201.

[0049] Specifically, by arranging several water purifiers 2 in parallel on the tap water inlet pipe 1, the flexible combined use of the water purifiers 2 is realized. By controlling the working states of several water purifiers 2, it is convenient to meet the water consumption requirements in different scenarios and realize the stable control of water quality and water volume.

[0050] Embodiment 2:

[0051] Referring to Figure 1 , this embodiment further discloses:

[0052] A data acquisition module, which acquires the historical water purification data of the water purifier 2 and the corresponding number of water purifiers 2 used. The historical water purification data is acquired under the condition that the water body is purified up to standard. The historical water purification data includes the flow data per unit time of the tap water inlet pipe 1, the water pressure data per unit time and the pollution coefficient;

[0053] The generation method of the pollution coefficient is as follows:

[0054]

[0055] In the formula, W x is the pollution coefficient, Z dLet the turbidity of the water body in the tap water inlet pipe 1 be Tur, the pH value of the water body in the tap water inlet pipe 1 be pH, and the dissolved oxygen content in the water body in the tap water inlet pipe 1 be Ry. and are both weight coefficients. and are both greater than 0.

[0056] It should be noted that the greater the pollution coefficient, the lower the filtration efficiency, and the more purifiers 2 are required. Conversely, the greater the turbidity of the water body, the more serious the pollution of the water body, and the greater the pollution coefficient. Conversely, the greater the value of |pH - 7.5|, the greater the acidity or alkalinity of the water body, and the greater the pollution coefficient. Conversely,

[0057] The dissolved oxygen content of the water body is one of the important indicators to measure the water quality, which directly affects the survival and reproduction of organisms in the water body. The water body with a high dissolved oxygen content is usually considered a high-quality water body because it can meet the survival needs of organisms in the water. Therefore, the greater the dissolved oxygen content in the water body, the lower the pollution of the water body. Conversely,

[0058] Among them, the turbidity and pH of the water body are directly collected by a turbidity sensor and a pH sensor installed in the tap water inlet pipe 1 (the turbidity sensor and the pH sensor are not shown in the figure), and the dissolved oxygen content in the water body is collected by a dissolved oxygen meter installed in the tap water inlet pipe 1.

[0059] It should be noted that the size of the weight coefficient is a specific value obtained by quantifying each data for subsequent comparison. Regarding the size of the weight coefficient, it depends on the number of comprehensive parameters and the weight coefficients initially set by those skilled in the art for each set of comprehensive parameters.

[0060] The model training module trains and predicts a machine learning model for the number of purifiers 2 used based on historical water purification data of the water body, collects real-time water purification data of the water body, and predicts the number of purifiers 2 used based on the trained machine learning model.

[0061] The analysis and control module controls the solenoid valves 211 provided on the corresponding number of water inlet pipes 21 to open based on the predicted number of purifiers 2 used.

[0062] The training method of the machine learning model for predicting the number of purifiers 2 used includes:

[0063] Converting the collected historical water purification data of the water body and the number of purifiers 2 used into a corresponding set of feature vectors.

[0064] The historical water purification data of the water purifier 2 collected is used as the input of the machine learning model. The machine learning model outputs the number of water purifiers 2 corresponding to each set of historical water purification data. Taking the actual number of water purifiers 2 used corresponding to each set of historical water purification data as the prediction target, and minimizing the loss function value of the machine learning model as the training target, the training stops when the loss function value of the machine learning model is less than or equal to the preset target loss value.

[0065] The machine learning model is any one of a deep neural network model or a deep belief network model, and the loss function value of the machine learning model is the mean square error;

[0066] The mean square error is one of the commonly used loss functions. By minimizing the loss function as the target to train the model, the first machine learning model can better fit the data, thereby improving the performance and accuracy of the model;

[0067] In the loss function, MSE1 is the loss function value of the machine learning model, x is the feature vector group number; m is the number of feature vector groups; y x is the number of uses corresponding to the x-th group of feature vectors, is the number of uses corresponding to the x-th group of feature vectors in real time;

[0068] Other model parameters of the machine learning model, the target loss value, the optimization algorithm, the ratio of the training set, test set, and validation set, and the optimization of the loss function are all obtained through actual engineering implementation and continuous experimental tuning.

[0069] Specifically, for this internal pressure type anti-piling intelligent water purifier, the machine learning model is trained with the historical water purification data of the water purifier 2 and the number of water purifiers 2 used. Based on the trained machine learning model, the usage status of several water purifiers 2 within a unit time is predicted. Thus, based on the real-time collected water purification data and the trained machine learning model, the usage status of several water purifiers 2 is controlled to achieve intelligent coordination of the working status of several parallel-connected water purifiers 2 and realize stable control of water quality and water volume.

[0070] Embodiment 3:

[0071] Refer to Figure 1 - Figure 2 This embodiment further discloses: a backwashing assembly 4 and a control unit;

[0072] The backwashing assembly 4 includes:

[0073] A flushing water storage tank 41, which is used to store the filtered water for flushing the water purifier 2;

[0074] A flushing main pipe 42, which is conductively connected to the flushing water storage tank 41;

[0075] The flushing branch pipe 43 has one end conductively connected to the flushing main pipe 42 and the other end conductively connected to the water purifier 2. A flushing volume control valve 44 is provided on the flushing branch pipe 43.

[0076] The control unit includes:

[0077] A data recording module for recording the usage time information within a unit cycle of a number of water purifiers 2 and the total amount of purified water of the water purifier 2 within the unit cycle;

[0078] A data analysis module for generating a backwashing coefficient based on the usage time information, the total amount of purified water information, the unit cycle, and the pollution coefficient, and judging and generating corresponding flushing water volume level information according to the backwashing coefficient;

[0079] A control module for controlling the opening time of the corresponding flushing volume control valve 44 according to the flushing water volume level information;

[0080] The method for recording the usage time within a unit cycle of a number of water purifiers 2 and the total amount of purified water of the water purifier 2 within the unit cycle includes:

[0081] Mark a number of parallel water purifiers 2 in sequence, and mark the number of water purifiers 2 as J1, J2, ……, J n ;

[0082] Obtain the usage time and the total amount of purified water of each water purifier 2 within the unit cycle TZ;

[0083] Among them, the unit cycle TZ is the backwashing cycle of a number of water purifiers 2. Preferably, it is one week (7 days).

[0084] It should be noted that the usage time is recorded by a set timer (not shown in the figure). When the solenoid valve 211 on the water inlet pipe 21 connected to the water purifier 2 is opened, the timer is controlled to start timing, and when it is closed, the timer is controlled to close at the same time. The recording cycle of the timer is the unit cycle TZ;

[0085] The total amount of purified water is counted by a flow meter provided in the drain pipe 22.

[0086] The generation method of the backwashing coefficient is as follows:

[0087]

[0088] Among them, FK n is the backwashing coefficient of the nth water purifier 2, T n is the usage time of the nth water purifier 2 within the unit cycle, SZ n is the total amount of purified water of the nth water purifier 2 within the unit cycle, and TZ is the unit cycle data of the nth water purifier 2, and are both weight coefficients, and are both greater than 0.

[0089] The magnitudes of the weight coefficients are specific values obtained by quantifying each data, which facilitates subsequent comparison. Regarding the magnitudes of the weight coefficients, they depend on the number of comprehensive parameters and the weight coefficients initially set by those skilled in the art for each group of comprehensive parameters.

[0090] The method for determining the corresponding flushing water volume level information based on the backwashing coefficient includes:

[0091] Presetting backwashing coefficient thresholds F1 and F2, where F1 < F2;

[0092] When FK n ≤ F1, at this time, the data analysis module generates first-level flushing water volume information;

[0093] When F1 < FK n < F2, at this time, the data analysis module generates second-level flushing water volume information;

[0094] When FK n ≥ F2, at this time, the data analysis module generates third-level flushing water volume information;

[0095] Among them, the flushing water volumes corresponding to the first-level flushing water volume information, the second-level flushing water volume information, and the third-level flushing water volume information increase in sequence.

[0096] At the bottom center of the water purifier 2, a sewage discharge pipe 5 is conductively connected, which is used to discharge the sewage generated by backwashing. A control valve 51 is provided on the sewage discharge pipe 5.

[0097] Specifically, through the setting of the backwashing assembly 4 and the control unit, during use, the data recording module can obtain the usage time and the purified water volume of each water purifier 2, and then calculate to obtain the backwashing coefficient, so as to determine and generate the corresponding flushing water volume level information according to the backwashing coefficient. Specifically, different levels of flushing water volume information with different flushing water volumes are generated according to the usage time, the purified water volume of each water purifier 2, the time of each unit cycle, and the pollution coefficient of the water body, so as to realize targeted backwashing for each water purifier 2, ensure its flushing effect, and also save flushing water.

[0098] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and the descriptions in the specification are only used to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An internal pressure type anti-deposition intelligent water purifier, comprising a tap water inlet pipe (1), a plurality of water purifiers (2) and a water outlet pipe (3), wherein the water inlet pipes (21) of the plurality of water purifiers (2) are interconnected with the tap water inlet pipe (1), the drainage pipes (22) of the plurality of water purifiers (2) are interconnected with the water outlet pipe (3), and the plurality of water inlet pipes (21) are provided with solenoid valves (211) for controlling the opening or closing of the water inlet pipes (21), characterized in that: Also includes: A data collection module collects historical water purification data of the water purifier (2) and the corresponding number of water purifiers (2) in use, wherein the historical water purification data is collected when the water body is purified up to the standard, and the historical water purification data includes flow data per unit time of the tap water inlet pipe (1), water pressure data per unit time and pollution coefficient; The pollution coefficient is generated as follows: Where W X is the pollution coefficient, Z d is the turbidity of the water in the tap water inlet pipe (1), PH is the acidity and alkalinity of the water in the tap water inlet pipe (1), Ry is the dissolved oxygen content in the water in the tap water inlet pipe (1), and are weight coefficients, and All are greater than 0; A model training module, based on historical water purification data, trains a machine learning model for predicting the number of water purifiers (2) in use, collects real-time water purification data, and predicts the number of water purifiers (2) in use based on the trained machine learning model; The analysis control module controls the opening of a corresponding number of solenoid valves (211) provided on the water inlet pipes (21) based on the predicted number of water purifiers (2) in use.

2. The internal pressure anti-deposition intelligent water purifier according to claim 1, characterized in that: The training method of the machine learning model for predicting the number of water purifiers (2) in use includes: Convert the collected historical water purification data of the water purifier (2) and the number of times the water purifier (2) is used into a corresponding set of feature vectors; The collected historical water purification data of the water purifier (2) is used as the input of the machine learning model, the machine learning model takes the number of water purifiers (2) in use corresponding to each set of historical water purification data as the output, takes the number of water purifiers (2) in use actually corresponding to each set of historical water purification data as the prediction target, takes minimizing the loss function value of the machine learning model as the training target, and stops training when the loss function value of the machine learning model is less than or equal to a preset target loss value.

3. The internal pressure anti-deposition intelligent water purifier according to claim 1, characterized in that: It also includes a backwashing component (4) and a control unit; The backwashing assembly (4) comprises: A flushing water storage tank (41) for storing filtered water for flushing the water purifier (2); A flushing main pipe (42) which is conductively connected to the flushing water storage tank (41); A flushing branch pipe (43) has one end connected to the flushing main pipe (42) and the other end connected to the water purifier (2). A flushing volume control valve (44) is provided on the flushing branch pipe (43).

4. The internal pressure anti-deposition intelligent water purifier according to claim 3, characterized in that: The control unit comprises: A data recording module, used to record usage time information of a plurality of water purifiers (2) within a unit period and total amount of water purified by the water purifiers (2) within a unit period; The data analysis module generates a backwash coefficient based on the usage time information, the total amount of purified water, the unit cycle and the pollution coefficient, and generates corresponding flushing water level information based on the backwash coefficient; The control module controls the opening time of the corresponding flushing volume control valve (44) according to the flushing water volume level information.

5. The internal pressure anti-deposition intelligent water purifier according to claim 1, characterized in that: The method for recording the usage time of a plurality of water purifiers (2) within a unit period and the total amount of water purified by the water purifiers (2) within the unit period comprises: The plurality of water purifiers (2) connected in parallel are marked in sequence, and the plurality of water purifiers (2) are marked as J1, J2, ..., J1 in the order of use. n ; Obtain the usage time and total amount of purified water of each water purifier (2) within the unit period TZ; The unit period TZ is the backwash period of a number of water purifiers (2).

6. The internal pressure anti-deposition intelligent water purifier according to claim 4, characterized in that: The backwash coefficient is generated as follows: Among them, FK n is the backwash coefficient of the nth water purifier (2), T n is the usage time per unit cycle of the nth water purifier (2), SZ n is the total amount of purified water per unit cycle of the nth water purifier (2), TZ is the unit cycle data of the nth water purifier (2), and are weight coefficients, and Both are greater than 0.

7. The internal pressure anti-deposition intelligent water purifier according to claim 1, characterized in that: The method for generating corresponding flushing water level information according to the backwashing coefficient includes: Preset backwash coefficient thresholds F1 and F2, where F1 < F2; When FK n ≤F1, at this time, the data analysis module generates the first-level flushing water volume information; When F1<FK n <F2, at this time, the data analysis module generates secondary flushing water volume information; When FK n ≥F2, at this time, the data analysis module generates three-level flushing water volume information; Among them, the flushing water volumes corresponding to the first-level flushing water volume information, the second-level flushing water volume information and the third-level flushing water volume information increase sequentially.

8. The internal pressure anti-deposition intelligent water purifier according to claim 4, characterized in that: A sewage pipe (5) is connected to the center of the bottom of the water purifier (2) and is used to discharge sewage generated by backwashing. A control valve (51) is provided on the sewage pipe (5).

9. The internal pressure anti-deposition intelligent water purifier according to claim 4, characterized in that: The water purifier (2) is composed of a cylindrical outer shell (201) and an internal pressure filter element (202) arranged in the cylindrical outer shell (201).

Images